Kinniku Buster | Concept LoRA<h3 id="heading-3">KIIIIIIINNNIIIIIKU BUUSTER!</h3>Weight can go from 0.8 up to 1. I recommend 1. Good results are around 1/6 given that the dataset was really small.Use of width 768 and height 512 recommended.Will need inpainting/photoshop to fix flaws, waiting on preview to see if a v2 is possible! Trigger Word:KinnikuBusterHow to use LoRA's in auto1111:<ul><li>Download LoRA</li><li>Copy the file to <code>stable-diffusion-webui/models/lora</code></li><li>Select your LoRA and use the triggerword</li><li>Make sure to change the weight if needed (by default it's <code>:1</code>)</li><li>Have Fun!</li></ul><h3 id="heading-3329">Why is my results different from yours?</h3><ul><li>Enable quantization in K samplers in your settings</li><li>Keep your prompts simple and correct<ul><li><a target="_blank" rel="ugc" href="https://github.com/DominikDoom/a1111-sd-webui-tagcomplete">Tag auto complete extension </a>to help you with your tags</li><li>Neg embedding have a great impact on the output of a model</li><li>Depending on the one you are using, results will be different.</li><li>I mainly use <a target="_blank" rel="ugc" href="https://civarchive.com/models/81575/amazing-embeddings-fcnegative-fcportrait-suite">fitCorder </a>embeddings for negative :)</li></ul></li></ul>You can support me on <a target="_blank" rel="ugc" href="https://ko-fi.com/astrea_pixie">Ko-Fi</a> and <a target="_blank" rel="ugc" href="https://www.patreon.com/AstreaPixie">Patreon</a>

Files with SHA256: 6b0bd3bcf0e71ecff1e3158c58627746f6bf0f274139553d760ef4a9e81eaf63